Adaptive Dynamic Filtering Network for Image Denoising
Proceedings of the AAAI Conference on Artificial Intelligence · 26.06.2023 · 37 (2) · 2227-2235
DOI: 10.1609/aaai.v37i2.25317 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 26.06.2023. Verfasst von Hao Shen und 2 weiteren Autor:innen. Die Arbeit wurde bisher 51-mal zitiert (Crossref).
Abstract (Originalsprache)
In image denoising networks, feature scaling is widely used to enlarge the receptive field size and reduce computational costs. This practice, however, also leads to the loss of high-frequency information and fails to consider within-scale characteristics. Recently, dynamic convolution has exhibited powerful capabilities in processing high-frequency information (e.g., edges, corners, textures), but previous works lack sufficient spatial contextual information in filter generation. To alleviate these issues, we propose to employ dynamic convolution to improve the learning of high-frequency and multi-scale features. Specifically, we design a spatially enhanced kernel generation (SEKG) module to improve dynamic convolution, enabling the learning of spatial context information with a very low computational complexity. Based on the SEKG module, we propose a dynamic convolution block (DCB) and a multi-scale dynamic convolution block (MDCB). The former enhances the high-frequency information via dynamic convolution and preserves low-frequency information via skip connections. The latter utilizes shared adaptive dynamic kernels and the idea of dilated convolution to achieve efficient multi-scale feature extraction. The proposed multi-dimension feature integration (MFI) mechanism further fuses the multi-scale features, providing precise and contextually enriched feature representations. Finally, we build an efficient denoising network with the proposed DCB and MDCB, named ADFNet. It achieves better performance with low computational complexity on real-world and synthetic Gaussian noisy datasets. The source code is available at https://github.com/it-hao/ADFNet.
Zitieren
APA
Shen, H., Zhao, Z., & Zhang, W. (2023). Adaptive Dynamic Filtering Network for Image Denoising. Proceedings of the AAAI Conference on Artificial Intelligence, 37(2), 2227-2235. https://doi.org/10.1609/aaai.v37i2.25317
Vancouver
Shen H, Zhao Z, Zhang W. Adaptive Dynamic Filtering Network for Image Denoising. Proceedings of the AAAI Conference on Artificial Intelligence. 2023;37(2):2227-2235. doi:10.1609/aaai.v37i2.25317
BibTeX
@article{Shen2023,
author = {Shen, Hao and Zhao, Zhong-Qiu and Zhang, Wandi},
title = {Adaptive Dynamic Filtering Network for Image Denoising},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2023},
volume = {37},
number = {2},
pages = {2227--2235},
doi = {10.1609/aaai.v37i2.25317}
}
EUVIMED